191 citations
- Chongqing Normal UniversityCN27 papers
- Fudan UniversityCN18 papers
- Shanxi UniversityCN17 papers
- Shanghai Jiao Tong UniversityCN13 papers
- University of Shanghai for Science and TechnologyCN13 papers
- Jinan Institute of Quantum TechnologyCN10 papers
- Chinese Academy of SciencesCN8 papers
- Allen Institute for Brain ScienceUS6 papers
- Shanxi University of Traditional Chinese MedicineCN6 papers
- Beihang UniversityCN5 papers
- New York University ShanghaiCN5 papers
- Shanghai Institute of Applied PhysicsCN5 papers
6 papers · 1 filter
Aspect-Based Sentiment Evolution and its Correlation with Review Rounds in Multi-Round Peer Reviews: A Deep Learning Approach
Ruxue Hana, Haomin Zhoua, Jiangtao Zhong +1
Mining sentiment information from the textual content of peer review comments offers valuable insights into the scientific evaluation process. However, previous studies are often c…
Logic-Regularized Verifier Elicits Reasoning from LLMs
Xinyu Wang, Changzhi Sun, Lian Cheng +4
Verifiers are crucial components for enhancing modern LLMs' reasoning capability. Typicalverifiers require resource-intensive superviseddataset construction, which is costly and fa…
Embedding Enhancement via Fine-Tuned Language Models for Learner-Item Cognitive Modeling
Yuanhao Liu, Zihan Zhou, Kaiying Wu +5
Learner-item cognitive modeling plays a central role in the web-based online intelligent education system by enabling cognitive diagnosis (CD) across diverse online educational sce…
Mask-GCG: Are All Tokens in Adversarial Suffixes Necessary for Jailbreak Attacks?
Junjie Mu, Zonghao Ying, Zhekui Fan +6
Jailbreak attacks on Large Language Models (LLMs) have demonstrated various successful methods whereby attackers manipulate models into generating harmful responses that they are d…
Building from Scratch: A Multi-Agent Framework with Human-in-the-Loop for Multilingual Legal Terminology Mapping
Lingyi Meng, Maolin Liu, Hao Wang +3
Accurately mapping legal terminology across languages remains a significant challenge, especially for language pairs like Chinese and Japanese, which share a large number of homogr…
EMNLP: Educator-role Moral and Normative Large Language Models Profiling
Yilin Jiang, Mingzi Zhang, Sheng Jin +3
Simulating Professions (SP) enables Large Language Models (LLMs) to emulate professional roles. However, comprehensive psychological and ethical evaluation in these contexts remain…